umesharaddy

Dr. Umesharaddy Radder received the Bachelor Degree in Electronics and Communication Engineering from Visvesvaraya Technological University,Belgaum, Karnataka, India, in 2003 and M.Tech degree in VLSI Design and Embedded Systems from Visvesvaraya Technological University, Belgaum, Karnataka, India, in 2006. Received Doctor of Philosophy in field of VLSI Design
and communication in the year 2018 from Visvesvaraya Technological University, Belgaum, Karnataka, India. He is worked as lecturer in Sri Venkateshwara College of Engineering in the year 2006 to 2007 and Assistant Professor in the Department of
Telecommunication Engeneering, M.S.Ramaiah Institute of Technology, Bangalore, Karnataka, India from 2007 to 2022.
He is worked as Senior Design Engineer and Technical Manager in FrenusTech Pvt Ltd and PrvegaSemi Pvt Ltd in the VLSI R & D Center, from 2022 to 2024 and also worked as Associate Professor (Adjunct) in the Dept. Of ECE, GSSSIETW in the year 2023 to 2024, Mysore.

EDUCATION

Ph. D in VLSI Design

RESEARCH, TEACHING, or OTHER INTERESTS

Engineering, Hardware and Architecture

Scopus Publications

Reinforcement-led digital twin optimization for secure operation in cyber-physical grids
Mahesh Kumar N, G Saranya, Umesharaddy Radder, Keerthy N, Deepak G, Vasanthi Sundaramurthy, A Divya, Raj Kumar Masih
Electric Power Systems Research, 2026
Spatial-temporal learning using GCN-BiLSTM for accurate renewable energy power prediction
T.R. Vedhavathy, Umesharaddy Radder, B. Ben Sujitha, Brajesh kumar singh, Mahesh Singh, S. Jayaprakash
Electric Power Systems Research, 2026
Predicting Adult Zebrafish Anxiety Behaviours Using the Behavioural Deep Context Analysis Network (BDCAN)
Vanaja, Umesharaddy Radder, Bairy Mahender, Ravi Kumar Saidala, Clarine Renie Delilah J Jacob Antony, Bhuvaneswari Arunagiri
Proceedings of the 2025 11th International Conference on Communication and Signal Processing Iccsp 2025, 2025
The BDCAN model predicts adult zebrafish anxiety-related behaviors using machine learning. Thus, knowing zebrafish behavior patterns is important in neurosciences, pharmacology, and anxiety disorders and therapies. The proposed BDCAN uses multi-modal spatio-temporal feature extraction and adaptive attention techniques to identify and characterize zebrafish anxiety subtleties based on BDCAN3D. Anxiety-related behaviors including irregular swimming, freezing, and thigmotaxis may be assessed using movement trajectory metrics like speed and spatial preferences identified by the network. The model design uses Convolutional Neural Networks to capture spatial characteristics, Long Short-Term Memory Networks to analyze temporal variables, and an attention layer to identify critical behavioral transitions. BDCAN has 98% accuracy in identifying anxiety-like behaviors with proper class labeling and filtering out sounds during testing.State-of-the-art deep machine learning can investigate zebrafish behavior with improved resolution and temporal stochastic dynamics. Aquatic behavioural analysis relies on the innovative, precise, and fast BDCAN framework to study anxiety and therapeutic chemicals in preclinical animals.
Improved Cancer miRNA Biomarker Classification through Adaptive Multi-Resolution Temporal Attention Network (AMRTA Net) with Efficient Transfer Learning
Vanaja, Ravi Kumar Saidala, Umesharaddy Radder, Varalakshmi T, Nisha Robin Rohit, Bhuvaneswari Arunagiri
Proceedings of the 2025 11th International Conference on Communication and Signal Processing Iccsp 2025, 2025
Cancer diagnosis and treatment rely on biomarker discovery, and miRNA profiles are significant tools. The Adaptive Multi-Resolution Temporal Attention Network (AMRTA Net) is a novel miRNA biomarker classification method. AMRTA Net uses better multi-resolution feature extraction and fine-tuned temporal attention to represent miRNA data with fine-grained and global characteristics. AMRTA Net's Hierarchical Resolution Analysis Module analyzes biomarker data at several resolutions while concentrating on critical aspects for cancer classification. A Customizable Transfer Learning (CTL) architecture improves model performance. To effectively learn biomarker-related information, it adaptively modifies just the final few layers of a pre-trained deep neural network. The method uses a Temporal Stability Optimization (TSO) loss function to reduce feature extraction shift at various time points to counteract temporal volatility in miRNA data sets. Biomedical researchers typically lack labeled samples, hence a successful Hybrid Semi-Supervised Learning Strategy adds pseudo-labelled data to the training set. In experimental investigation, AMRTA Net outperformed other approaches in cancer miRNA dataset categorization with 97.2% accuracy. The model is ideal for biomedical diagnostics because to its noise tolerance and strong scalability for big data sets. AMRTA Net, a precision medicine breakthrough, classifies miRNA biomarkers intelligently and accurately using adaptive learning, multi-resolution analysis, and temporal attention.
Innovations in Stroke Evaluation: A Diagnostic System implementing Neuroimage-Based Machine Learning
Ravi Kumar Saidala, Anil Kumar Reddy Tetali, Umesharaddy Radder, Prabhu Shankar B, Chethana R M, T Chalama Reddy
3rd International Conference on Advances in Computing Communication and Materials Icaccm 2024, 2024
Even as diseases of the circulation in the brain particularly-strokes rank amongst leading causes of death and disability in the world they are not completely untreatable maladies. The early detection and management of cases of the disease are critical for reducing the effects of stroke and optimizing the patients’ experience. Recent focus has been made on the application of the machine learning approaches for the stroke identification process. Its objective comprises such goals as determining helpful approaches, methodologies, and characteristics that help medical practitioners make proper decisions about the treatment and prevention of stroke. In this way, by our initiative, the new, efficient system for early stroke detection using primary brain CT-scan has been developed. This system integrates genetic algorithm made use of in selecting the ideal features with a bidirectional long short-term memory (BiLSTM) network to locate and confirm diseases in their preliminary stages- Strokes here. This system combines genetic algorithm and neural networks to identify the features that are important for classification and pass them to the BiLSTM model. In addition, we could perform the comparative analyses with the "matched" techniques of the first kind, which is based on the systematic comparison with the tests used in the classical tradition of mathematical statistics.
Supervised Deep Learning Methodology for Autonomous Vehicle Routing
Ravi Kumar Saidala, Subrahmanya S Meduri, Anil Kumar Reddy Tetali, Rama Devi Burri, Umesharaddy Radder, Gaurav Vishnu Londhe
3rd International Conference on Advances in Computing Communication and Materials Icaccm 2024, 2024
Automated driving is a revolutionary technology that is fundamentally changing worldwide transportation networks. An essential component of autonomous vehicle operation is path planning, which guarantees secure and effective navigation across intricate and ever-changing surroundings. This work presents an innovate neural network design that integrates deep Q-learning with policy gradients, therefore improving the current deep reinforcement learning paradigm. This methodology allows the self-driving vehicle to acquire knowledge and adjust to intricate situations using huge quantities of data, strict adherence to demanding global criteria. To verify the efficacy of our suggested approach, we performed simulations using both realistic and benchmark scenarios. The findings illustrate that our methodology greatly improves the vehicle's performance in difficult circumstances while upholding a commendable degree of safety. An analysis was conducted on important parameters like route completion time, energy usage, and adaptation to changing environmental circumstances. This approach demonstrates superior performance compared to both conventional and modern autonomous driving methods, therefore highlighting its capacity to propel the field of route planning in autonomous systems forward. The present study makes a valuable contribution to the advancement of autonomous driving technology by the introduction of an advanced deep learning framework that enhances path planning and decision-making capabilities.
Real-Time Neural Network System for Identifying Visual Learners from Raw EEG Data
Ravi Kumar Saidala, Satyanarayanareddy Marri, Umesharaddy Radder, Chethana R M, Ramesh Reddy Bojja, Prabhu Shankar B
3rd International Conference on Advances in Computing Communication and Materials Icaccm 2024, 2024
Presenting a new real-time learner identification system, this study uses EEG signals in its unprocessed form to feed a neural network. Conventional analysis of EEG involves pre-processing signals to get information which is contrary to deep learning algorithm by providing easy extractable information fed into machine’s visual processing. Next, there were LSTM, LSTM-CNN and LSTM-FCNN models which were deployed and experimented to locate high-level characteristics in the EEG signals closely related to learning preferences for visuals. EEG data were obtained from 34 healthy subjects under different conditions but with most focus being given to data obtained while the subjects eyes were closed as this data is relatively pure of external interferences and reflect quite well the cognitive states of a subject. Real-time operations of the deep learning models were carefully designed to manage the different signal lengths for efficient and less computational. Out of all the models, LSTM-CNN was found to be the most effective with the model accuracy of 94%, sensitivity of 80%, specificity of 92% and the model F1 score of 94%. These results support the ability of the system to identify visual learning type from the EEG signals and open a way for using the system in individual learning and cognitive assessment.
Discovery of concealed patterns in skin cancer detection using deep learning techniques
Ravi Kumar Saidala, Putta Srivani, Umesharaddy Radder, Rama Devi Burri, Prabhu Shankar B, Anil Kumar Reddy Tetali
3rd International Conference on Advances in Computing Communication and Materials Icaccm 2024, 2024
Cancer, known for its resilience, is the outcome of unregulated cellular proliferation in the human body, leading to the losses of numerous lives and causing significant concern within society. Among all types of cancer, the one that arises in the outermost layer of the skin, generally referred to as skin cancer, is most widespread. Machine learning has made significant contributions in the past, but these approaches have mostly depended on well-designed techniques. The introduction of the proposed model represents a significant advancement, since it effectively addresses the issue of feature extraction, either whole or partially, and significantly reduces the amount of effort required. The present study utilizes convolutional deep neural networks to analyse skin cancer using the publicly available ISIC dataset, emphasizing the criticality of early detection. Every individual machine learning model has inherent limitations, but the integration of these models leads to more reliable outcomes. Ensemble learning is the process of combining as many models as feasible, which leads to enhanced decision making and higher prediction accuracy. The objective of this work is to investigate the viability of combining the VGG, Caps Net, and Reset models for the purpose of cancer detection. As seen by the findings, the combined model outperforms individual models for each genre. The present work not only advances the technology used for the detection of skin cancer but also expands the potential for early diagnosis of other diseases.
Synthesis, spectroscopic (FT-IR, FT-Raman, NMR), reactivity (ELF, LOL and Fukui) and docking studies on 3-(2‑hydroxy-3‑methoxy-phenyl)-1-(3-nitro-phenyl)-propenone by experimental and DFT methods
Shivaraj B. Radder, Raveendra Melavanki, Umesharaddy Radder, Sudhir M. Hiremath, Raviraj Kusanur, Seema S. Khemalapure
Journal of Molecular Structure, 2022
Efficient MODEM Design for SDR Application
Umesharaddy Radder, Ashwini R Kumbar
2021 6th International Conference on Recent Trends on Electronics Information Communication and Technology Rteict 2021, 2021
Efficient modulation and demodulation(MODEM) design is required and essential for Software defined radio (SDR) application. In the proposed design not only reducing the hardware complexity but it will reduce the power consumption also. Optimization of the MODEM hardware is done through three important design metrics through time (speed / frequency), power consumption and area(size). To develop a product that can transmit the signal to a longer distance without loss of original information with high bandwidth. Also to develop a smart MODEM system that can consume very less area and power. The project aims at presenting a method to design an efficient QPSK modulator and demodulator system with and without AWGN(Additive white Gaussian Noise) and RRC filter (Root Raised cosine filter) for SDR application. The entire QPSK system has been simulated in Xilinx 14.7 version software and Vivado software. Finally implemented on to the Spartan 6 FPGA Board and Zynq 7000 based ZED board. the results depicts that the proposed design can greatly improve the speed and reduce the latency and improve the frequency of operation about 20% when compared with the existing method.
Design and Development of Precoding Algorithm
Umesharaddy Radder, S.G. Shivaprasad Yadav, B K Sujatha, Anusha Hiremath
Proceedings 5th IEEE International Conference on Recent Trends in Electronics Information and Communication Technology Rteict 2020, 2020
Performance Improvement of QPSK MODEM in AWGN Channel Implemented in FPGA
Umesharaddy Radder, B.K. Sujatha
2019 4th IEEE International Conference on Recent Trends on Electronics Information Communication and Technology Rteict 2019 Proceedings, 2019

RECENT SCHOLAR PUBLICATIONS

Synthesis, spectroscopic (FT-IR, FT-Raman, NMR), reactivity (ELF, LOL and Fukui) and docking studies on 3-(2‑hydroxy-3‑methoxy-phenyl)-1-(3-nitro-phenyl)-propenone by …
SB Radder, R Melavanki, U Radder, SM Hiremath, R Kusanur, ...
Journal of Molecular Structure 1255, 132443 , 2022
2022
Citations: 40
The IoT based PPG Signal Classification System for Acute Audio-Visual Stimulus Induced Stress
KV Suma, HSN Murthy, U Radder, P Suma
Webology 19 (1) , 2022
2022
Citations: 1
Efficient MODEM Design For SDR Application
U Radder, AR Kumbar
2021 International Conference on Recent Trends on Electronics, Information … , 2021
2021
Citations: 1
Design and development of precoding algorithm
U Radder, SGS Yadav, BK Sujatha, A Hiremath
2020 International Conference on Recent Trends on Electronics, Information … , 2020
2020
Citations: 1
Performance Improvement of QPSK MODEM in AWGN Channel Implemented in FPGA
U Radder, BK Sujatha
2019 4th International Conference on Recent Trends on Electronics … , 2019
2019
Performance Improvement of QPSK Modem with AWGN Implemented in FPGA
BKS Umesharaddy
International Journal of Scientific Engineering Research 8 (4) , 2017
2017
Citations: 1
Optimization of QPSK MODEM with AWGN implemented in FPGA
BK Sujatha
2017 International Conference on Inventive Systems and Control (ICISC), 1-6 , 2017
2017
Citations: 6
Performance improvement of QPSK modem implemented in FPGA
BK Sujatha
2015 International Conference on Smart Sensors and Systems (IC-SSS), 1-6 , 2015
2015
Citations: 5
Performance improvement of QPSK modem implemented in FPGA
BKS Umesharaddy
2015 International Conference on Smart Sensors and Systems (IC-SSS), 1-6 , 2015
2015
Citations: 2
Optimized modem design for SDR applications
LD Chougale, M Umesharaddy
2015 International Research Journal of Engineering and Technology (IRJET) , 2015
2015
Citations: 1
FPGA implementation of high throughput digital QPSK modulator using verilog HDL
K Anitha, Umesharaddy
International Journal of Advanced Computer Research 4 (14), 217-22 , 2014
2014
Citations: 22

MOST CITED SCHOLAR PUBLICATIONS

Synthesis, spectroscopic (FT-IR, FT-Raman, NMR), reactivity (ELF, LOL and Fukui) and docking studies on 3-(2‑hydroxy-3‑methoxy-phenyl)-1-(3-nitro-phenyl)-propenone by …
SB Radder, R Melavanki, U Radder, SM Hiremath, R Kusanur, ...
Journal of Molecular Structure 1255, 132443 , 2022
2022
Citations: 40
FPGA implementation of high throughput digital QPSK modulator using verilog HDL
K Anitha, Umesharaddy
International Journal of Advanced Computer Research 4 (14), 217-22 , 2014
2014
Citations: 22
Optimization of QPSK MODEM with AWGN implemented in FPGA
BK Sujatha
2017 International Conference on Inventive Systems and Control (ICISC), 1-6 , 2017
2017
Citations: 6
Performance improvement of QPSK modem implemented in FPGA
BK Sujatha
2015 International Conference on Smart Sensors and Systems (IC-SSS), 1-6 , 2015
2015
Citations: 5
Performance improvement of QPSK modem implemented in FPGA
BKS Umesharaddy
2015 International Conference on Smart Sensors and Systems (IC-SSS), 1-6 , 2015
2015
Citations: 2
The IoT based PPG Signal Classification System for Acute Audio-Visual Stimulus Induced Stress
KV Suma, HSN Murthy, U Radder, P Suma
Webology 19 (1) , 2022
2022
Citations: 1
Efficient MODEM Design For SDR Application
U Radder, AR Kumbar
2021 International Conference on Recent Trends on Electronics, Information … , 2021
2021
Citations: 1
Design and development of precoding algorithm
U Radder, SGS Yadav, BK Sujatha, A Hiremath
2020 International Conference on Recent Trends on Electronics, Information … , 2020
2020
Citations: 1
Performance Improvement of QPSK Modem with AWGN Implemented in FPGA
BKS Umesharaddy
International Journal of Scientific Engineering Research 8 (4) , 2017
2017
Citations: 1
Optimized modem design for SDR applications
LD Chougale, M Umesharaddy
2015 International Research Journal of Engineering and Technology (IRJET) , 2015
2015
Citations: 1
Performance Improvement of QPSK MODEM in AWGN Channel Implemented in FPGA
U Radder, BK Sujatha
2019 4th International Conference on Recent Trends on Electronics … , 2019
2019

CONSULTANCY

1.2 Lakhs

INDUSTRY EXPERIENCE

2 Years